ericm-db commented on code in PR #47524:
URL: https://github.com/apache/spark/pull/47524#discussion_r1704769194
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/IncrementalExecution.scala:
##########
@@ -242,7 +242,26 @@ class IncrementalExecution(
metadataWriter.write(metadata)
case _ =>
}
- statefulOp
+ statefulOp match {
+ case tws: TransformWithStateExec =>
+ // create map of columnFamilyName -> columnFamilyId
+ val newSchemas = schemaValidationResult.head.newSchemas
+ val columnFamilySchemas = newSchemas.map { case schema =>
+ schema.colFamilyName -> schema
+ }.toMap
+ StreamExecution.updateColumnFamilySchemas(
+ queryId, runId, columnFamilySchemas)
+ val stateInfo = tws.getStateInfo
+ tws.copy(stateInfo = Some(
+ stateInfo.copy(colFamilySchemas = columnFamilySchemas)))
+ case _ => statefulOp
+ }
+ case tws: TransformWithStateExec =>
Review Comment:
I assume we only want to populate for TWS, right?
We need this block since everything above is only executed for the first
batch of the run
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
